中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

69 records (took 0.02 seconds)

    Optimizing Inference Performance for Conformer
    44.
    发明申请
    Optimizing Inference Performance for Conformer 有权

    公开(公告)号：US20230130634A1

    公开(公告)日：2023-04-27

    申请号：US17936547

    申请日：2022-09-29

    Applicant: Google LLC

    Inventor： Tara N. Sainath ,  Rami Botros ,  Anmol Gulati ,  Krzysztof Choromanski ,  Ruoming Pang ,  Trevor Strohman ,  Weiran Wang ,  Jiahui Yu

    IPC: G10L15/16 ,  G10L15/22 ,  G10L15/06

    Abstract: A computer-implemented method includes receiving a sequence of acoustic frames as input to an automatic speech recognition (ASR) model. Here, the ASR model includes a causal encoder and a decoder. The method also includes generating, by the causal encoder, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by the decoder, a first probability distribution over possible speech recognition hypotheses. Here, the causal encoder includes a stack of causal encoder layers each including a Recurrent Neural Network (RNN) Attention-Performer module that applies linear attention.

    Emitting word timings with end-to-end models
    45.
    发明授权
    Emitting word timings with end-to-end models 有权

    公开(公告)号：US11580956B2

    公开(公告)日：2023-02-14

    申请号：US17204852

    申请日：2021-03-17

    Applicant: Google LLC

    Inventor： Tara N. Sainath ,  Basi Garcia ,  David Rybach ,  Trevor Strohman ,  Ruoming Pang

    IPC: G10L25/30 ,  G10L15/06 ,  G10L25/78

    Abstract: A method includes receiving a training example that includes audio data representing a spoken utterance and a ground truth transcription. For each word in the spoken utterance, the method also includes inserting a placeholder symbol before the respective word identifying a respective ground truth alignment for a beginning and an end of the respective word, determining a beginning word piece and an ending word piece, and generating a first constrained alignment for the beginning word piece and a second constrained alignment for the ending word piece. The first constrained alignment is aligned with the ground truth alignment for the beginning of the respective word and the second constrained alignment is aligned with the ground truth alignment for the ending of the respective word. The method also includes constraining an attention head of a second pass decoder by applying the first and second constrained alignments.

    TWO-PASS END TO END SPEECH RECOGNITION
    46.
    发明申请
    TWO-PASS END TO END SPEECH RECOGNITION 有权

    公开(公告)号：US20220238101A1

    公开(公告)日：2022-07-28

    申请号：US17616135

    申请日：2020-12-03

    Applicant: GOOGLE LLC

    Inventor： Tara N. Sainath ,  Yanzhang He ,  Bo Li ,  Arun Narayanan ,  Ruoming Pang ,  Antoine Jean Bruguier ,  Shuo-yiin Chang ,  Wei Li

    IPC: G10L15/16 ,  G10L15/05 ,  G10L15/22 ,  G10L15/06 ,  G06N3/08

    Abstract: Two-pass automatic speech recognition (ASR) models can be used to perform streaming on-device ASR to generate a text representation of an utterance captured in audio data. Various implementations include a first-pass portion of the ASR model used to generate streaming candidate recognition(s) of an utterance captured in audio data. For example, the first-pass portion can include a recurrent neural network transformer (RNN-T) decoder. Various implementations include a second-pass portion of the ASR model used to revise the streaming candidate recognition(s) of the utterance and generate a text representation of the utterance. For example, the second-pass portion can include a listen attend spell (LAS) decoder. Various implementations include a shared encoder shared between the RNN-T decoder and the LAS decoder.

    Neural Architecture Scaling For Hardware Accelerators
    47.
    发明申请
    Neural Architecture Scaling For Hardware Accelerators 有权

    公开(公告)号：US20220230048A1

    公开(公告)日：2022-07-21

    申请号：US17175029

    申请日：2021-02-12

    Applicant: Google LLC

    Inventor： Andrew Li ,  Sheng Li ,  Mingxing Tan ,  Ruoming Pang ,  Liqun Cheng ,  Quoc V. Le ,  Norman Paul Jouppi

    IPC: G06N3/04 ,  G06N3/08

    Abstract: Methods, systems, and apparatus, including computer-readable media, for scaling neural network architectures on hardware accelerators. A method includes receiving training data and information specifying target computing resources, and performing using the training data, a neural architecture search over a search space to identify an architecture for a base neural network. A plurality of scaling parameter values for scaling the base neural network can be identified, which can include repeatedly selecting a plurality of candidate scaling parameter values, and determining a measure of performance for the base neural network scaled according to the plurality of candidate scaling parameter values, in accordance with a plurality of second objectives including a latency objective. An architecture for a scaled neural network can be determined using the architecture of the base neural network scaled according to the plurality of scaling parameter values.

    Fast Emit Low-latency Streaming ASR with Sequence-level Emission Regularization
    48.
    发明申请
    Fast Emit Low-latency Streaming ASR with Sequence-level Emission Regularization 有权

    公开(公告)号：US20220122586A1

    公开(公告)日：2022-04-21

    申请号：US17447285

    申请日：2021-09-09

    Applicant: Google LLC

    Inventor： Jiahui Yu ,  Chung-cheng Chiu ,  Bo Li ,  Shuo-yiin Chang ,  Tara Sainath ,  Wei Han ,  Anmol Gulati ,  Yanzhang He ,  Arun Narayanan ,  Yonghui Wu ,  Ruoming Pang

    IPC: G10L15/06 ,  G10L15/22 ,  G10L15/30 ,  G10L15/16

    Abstract: A computer-implemented method of training a streaming speech recognition model that includes receiving, as input to the streaming speech recognition model, a sequence of acoustic frames. The streaming speech recognition model is configured to learn an alignment probability between the sequence of acoustic frames and an output sequence of vocabulary tokens. The vocabulary tokens include a plurality of label tokens and a blank token. At each output step, the method includes determining a first probability of emitting one of the label tokens and determining a second probability of emitting the blank token. The method also includes generating the alignment probability at a sequence level based on the first probability and the second probability. The method also includes applying a tuning parameter to the alignment probability at the sequence level to maximize the first probability of emitting one of the label tokens.

    SYNTHESIZING SPEECH FROM TEXT USING NEURAL NETWORKS
    50.
    发明申请
    SYNTHESIZING SPEECH FROM TEXT USING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20200051583A1

    公开(公告)日：2020-02-13

    申请号：US16058640

    申请日：2018-08-08

    Applicant: Google LLC

    Inventor： Yonghui Wu ,  Jonathan Shen ,  Ruoming Pang ,  Ron J. Weiss

    IPC: G10L25/30 ,  G10L13/047 ,  G10L13/08 ,  G10L25/18 ,  G06N3/08 ,  G06N3/04 ,  G06N5/04 ,  G06N7/00

    Abstract: Methods, systems, and computer program products for generating, from an input character sequence, an output sequence of audio data representing the input character sequence. The output sequence of audio data includes a respective audio output sample for each of a number of time steps. One example method includes, for each of the time steps: generating a mel-frequency spectrogram for the time step by processing a representation of a respective portion of the input character sequence using a decoder neural network; generating a probability distribution over a plurality of possible audio output samples for the time step by processing the mel-frequency spectrogram for the time step using a vocoder neural network; and selecting the audio output sample for the time step from the possible audio output samples in accordance with the probability distribution.

Patent Agency Ranking